© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63592
    Prev
    Next
    INDEX
    Explanations

    Jan

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    യോഗ
    0.42
     引き
    0.39
     souvenir
    0.39
    する場合
    0.37
    Personal
    0.36
    alne
    0.36
    smartphone
    0.36
    埕
    0.36
    icos
    0.36
    Tw
    0.36
    POSITIVE LOGITS
     rack
    0.40
    KI
    0.38
     Dewey
    0.38
     Rack
    0.38
     REACT
    0.37
     racking
    0.37
     Crossed
    0.37
    )]=
    0.36
    rack
    0.36
    ylar
    0.35
    Activations Density 0.000%

    No Known Activations